I'm excited to inform you that Zelig 3.2-0 includes five new models for complex
survey data, "normal.survey," "logit.survey,"
"probit.survey," "gamma.survey," and "poisson.survey." In
addition to conventional Zelig inputs, these models allow users with complex survey data
to input strata/cluster identification variables, replication weights, and/or existing
survey weights. These survey-weighted models are appropriate for any dataset generated
through something other than simple random sampling (i.e. stratified random sampling,
cluster sampling), and model estimates are automatically adjusted to take into account the
features of the survey design.
Full documentation for each model is available from
http://gking.harvard.edu/zelig/docs/index.html . It is my hope that these models will
allow researchers analyzing complex survey data to take advantage of Zelig's wide
array of useful features.
Nicholas Carnes
Graduate Student
Department of Politics
Princeton University
-
Zelig Mailing List, served by Harvard-MIT Data Center
Send messages: zelig(a)lists.gking.harvard.edu
[un]subscribe Options:
http://lists.gking.harvard.edu/?info=zelig
Zelig program information:
http://gking.harvard.edu/zelig/